Performing Decision-Theoretic Inference in Bayesian Network Ensemble Models
2013 (English)In: Twelfth Scandinavian Conference on Artificial Intelligence / [ed] Jaeger, M; Nielsen, TD; Viappiani, P, 2013, Vol. 257, 25-34 p.Conference paper (Refereed)
The purpose of this paper is to present a simple extension to an existing inference algorithm on influence diagrams (i.e. decision theoretic extensions to Bayesian networks) that permits these algorithms to be applied to ensemble models. The extension, though simple, is important because of the power and robustness that such ensemble models provide . This paper is intended principally as a 'recipe' that can be used even by those unfamiliar with the algorithms extended. Accordingly, I present the algorithms that the original contribution builds upon in full, though references are given to less concise renditions. Those familiar with these algorithms are invited to skip the elucidation. The consequence is a useful paper with more background and less original input than usual.
Place, publisher, year, edition, pages
2013. Vol. 257, 25-34 p.
, Frontiers in Artificial Intelligence and Applications, ISSN 0922-6389 ; 257
bayesian model averaging, influence diagrams, probabilistic models, graphical models, artificial intelligence, machine learning
IdentifiersURN: urn:nbn:se:uu:diva-211926DOI: 10.3233/978-1-61499-330-8-25ISI: 000343477100004ISBN: 978-1-61499-329-2OAI: oai:DiVA.org:uu-211926DiVA: diva2:670399
Twelfth Scandinavian Conference on Artificial Intelligence, 20-22 November, 2013, Aalborg, Denmark